Over-the-Air Federated Learning With Joint Privacy-Accuracy Optimization
Hexin Feng, Rui Wang, Erwu Liu, Wei Ni, Dusit Tao Niyato, Abbas Jamalipour · IEEE Transactions on Information Forensics and Security · 2025
Federated learning (FL) contributes to data privacy by not disclosing raw data, but encounters challenges of privacy leakage from local gradient uploading. This paper introduces a novel over-the-air computation (AirComp)-based FL system that balances privacy and accuracy by leveraging the waveform superposition and channel propagation characteristics of AirComp. Specifically, we derive the privacy leakage metric to explicitly account for the effects of waveform aggregation and communication noise. We analyze the convergence upper bound to capture model update errors stemming from artificial and communication noise. We formulate a new joint privacy-accuracy optimization problem by incorporating privacy leakage in the model training objective, guiding the learning process towards enhanced privacy protection. We then employ convex optimization techniques to derive the optimal power scaling and artificial noise intensity. Simulations demonstrate up to 80% reduction in privacy leakage compared to baselines under stringent privacy constraints, while maintaining competitive learning performance. Our method exhibits enhanced robustness under low signal-to-noise ratios, achieving 40% lower privacy leakage under equivalent privacy budgets.